LWG: DeepLoco

[From Rupert Young (2017.11.22 11.00)]

  This is what we have to deal with, counter and show that PCT can

do something similar, in a better way,

It is hierarchical and handles disturbances (watch “Main video”).

  I think this would certainly be a possibility of something to aim

at for our learning project.

···

http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

Regards,
Rupert

Crikey, that looks impressive. What’s the catch?

···

On Wed, Nov 22, 2017 at 11:04 AM, Rupert Young rupert@perceptualrobots.com wrote:

[From Rupert Young (2017.11.22 11.00)]

  This is what we have to deal with, counter and show that PCT can

do something similar, in a better way,

http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

It is hierarchical and handles disturbances (watch “Main video”).

  I think this would certainly be a possibility of something to aim

at for our learning project.


Regards,
Rupert

Dr Warren Mansell
Reader in Clinical Psychology

School of Health Sciences
2nd Floor Zochonis Building
University of Manchester
Oxford Road
Manchester M13 9PL
Email: warren.mansell@manchester.ac.uk

Tel: +44 (0) 161 275 8589

Website: http://www.psych-sci.manchester.ac.uk/staff/131406

Advanced notice of a new transdiagnostic therapy manual, authored by Carey, Mansell & Tai - Principles-Based Counselling and Psychotherapy: A Method of Levels Approach

Available Now

Check www.pctweb.org for further information on Perceptual Control Theory

[From Bruce Abbott (2017.11.22.1000 EST)]

Rupert Young (2017.11.22 11.00) –

RY: This is what we have to deal with, counter and show that PCT can do something similar, in a better way,

RY: http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

RY: It is hierarchical and handles disturbances (watch “Main video”).

RY: I think this would certainly be a possibility of something to aim at for our learning project.

BA: Impressive! However, looking a little deeper, I discovered that the project is all about developing physics-based computer animations rather than attempting to capture how real humans or other animals actually control their movements. PCT, in contrast, is all about understanding how the real systems work, based on their actual neuro-muscular systems. Given the “DeepLocoâ€? project’s goals, it is not surprising to find them using simulated “musclesâ€? that employ “optimizedâ€? insertion points (although they do show that models based on non-optimized insertion points will also work, although less well). The video showing behavior at various stages of learning reveals that good performance is not achieved until something on the order of 900 learning trials have been performed, so the learning algorithm does not seem to be particularly efficient, although it must be admitted that human learning of motor skills also requires a lot of practice. Algorithms that make use of complex computational techniques such as those employed in the DeepLoco project are unlikely to be implemented in our biological wetware. It seems that evolution has discovered powerful heuristic methods that achieve these goals without the mathematical complexities.

BA: That said, these researchers are in fact employing hierarchical control systems to carry out the simulated activities.

Bruce

Seen this folks?

https://www.theguardian.com/science/2017/oct/18/its-able-to-create-knowledge-itself-google-unveils-ai-learns-all-on-its-own

···

On Wed, Nov 22, 2017 at 11:04 AM, Rupert Young rupert@perceptualrobots.com wrote:

[From Rupert Young (2017.11.22 11.00)]

  This is what we have to deal with, counter and show that PCT can

do something similar, in a better way,

http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

It is hierarchical and handles disturbances (watch “Main video”).

  I think this would certainly be a possibility of something to aim

at for our learning project.


Regards,
Rupert

Dr Warren Mansell
Reader in Clinical Psychology

School of Health Sciences
2nd Floor Zochonis Building
University of Manchester
Oxford Road
Manchester M13 9PL
Email: warren.mansell@manchester.ac.uk

Tel: +44 (0) 161 275 8589

Website: http://www.psych-sci.manchester.ac.uk/staff/131406

Advanced notice of a new transdiagnostic therapy manual, authored by Carey, Mansell & Tai - Principles-Based Counselling and Psychotherapy: A Method of Levels Approach

Available Now

Check www.pctweb.org for further information on Perceptual Control Theory

[From Bruce Abbott (2017.11.24.1310 EST)]

Yes, I did see it, Warren, and replied to it on CSGnet; however, I never received a copy of my post, so perhaps it got lost in cyberspace. Did anyone on CSGnet see it? If not, I’ll repost.

By the way, I’m getting two copies of this thread, one through the CC: and one through CSGnet. Perhaps the CC: list could be culled to include only those not subscribed to CSGnet? Alternatively, just send those who expressed an interest and not CSGnet as a whole.

Bruce

···

From: Warren Mansell [mailto:wmansell@gmail.com]
Sent: Friday, November 24, 2017 5:30 AM
To: Rupert Young rupert@perceptualrobots.com
Cc: fred@nickols.us; Richard Marken rsmarken@gmail.com; Martin Taylor mmt-csg@mmtaylor.net; joh.orengo@protonmail.com; Sean Mulligan lack.of.inspiration@gmail.com; eetu.pikkarainen@oulu.fi; jlws.wright@optusnet.com.au; johnkirkland@gmail.com; richardpfau4153@aol.com; Bruce Abbott bbabbott@frontier.com; frank.lenk@gmail.com; D Goldstein davidmg@verizon.net; Huddy, Vyv v.huddy@ucl.ac.uk; csgnet@lists.illinois.edu
Subject: Re: LWG: DeepLoco

WM: Seen this folks?

https://www.theguardian.com/science/2017/oct/18/its-able-to-create-knowledge-itself-google-unveils-ai-learns-all-on-its-own

On Wed, Nov 22, 2017 at 11:04 AM, Rupert Young rupert@perceptualrobots.com wrote:

[From Rupert Young (2017.11.22 11.00)]

This is what we have to deal with, counter and show that PCT can do something similar, in a better way,

http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

It is hierarchical and handles disturbances (watch “Main video”).

I think this would certainly be a possibility of something to aim at for our learning project.

Regards,
Rupert

Dr Warren Mansell
Reader in Clinical Psychology

School of Health Sciences
2nd Floor Zochonis Building
University of Manchester
Oxford Road
Manchester M13 9PL
Email: warren.mansell@manchester.ac.uk

Tel: +44 (0) 161 275 8589

Website: http://www.psych-sci.manchester.ac.uk/staff/131406

Advanced notice of a new transdiagnostic therapy manual, authored by Carey, Mansell & Tai - Principles-Based Counselling and Psychotherapy: A Method of Levels Approach

Available Now

Check www.pctweb.org for further information on Perceptual Control Theory

Yes, I did see it, Warren, and
replied to it on CSGnet; however, I never received a copy of
my post, so perhaps it got lost in cyberspace. Did anyone
on CSGnet see it? If not, I’ll repost.

This is a resend, as it appears that the original was lost in transmission.

[From Bruce Abbott (2017.11.22.1000 EST)]

Rupert Young (2017.11.22 11.00) –

RY: This is what we have to deal with, counter and show that PCT can do something similar, in a better way,

RY: http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

RY: It is hierarchical and handles disturbances (watch “Main video”).

RY: I think this would certainly be a possibility of something to aim at for our learning project.

BA: Impressive! However, looking a little deeper, I discovered that the project is all about developing physics-based computer animations rather than attempting to capture how real humans or other animals actually control their movements. PCT, in contrast, is all about understanding how the real systems work, based on their actual neuro-muscular systems. Given the “DeepLocoâ€? project’s goals, it is not surprising to find them using simulated “musclesâ€? that employ “optimizedâ€? insertion points (although they do show that models based on non-optimized insertion points will also work, although less well). The video showing behavior at various stages of learning reveals that good performance is not achieved until something on the order of 900 learning trials have been performed, so the learning algorithm does not seem to be particularly efficient, although it must be admitted that human learning of motor skills also requires a lot of practice. Algorithms that make use of complex computational techniques such as those employed in the DeepLoco project are unlikely to be implemented in our biological wetware. It seems that evolution has discovered powerful heuristic methods that achieve these goals without the mathematical complexities.

BA: That said, these researchers are in fact employing hierarchical control systems to carry out the simulated activities.

Bruce

I did receive it.

···

On Fri, Nov 24, 2017 at 1:07 PM, Bruce Abbott bbabbott@frontier.com wrote:

[From Bruce Abbott (2017.11.24.1310 EST)]

Yes, I did see it, Warren, and replied to it on CSGnet; however, I never received a copy of my post, so perhaps it got lost in cyberspace. Did anyone on CSGnet see it? If not, I’ll repost.

By the way, I’m getting two copies of this thread, one through the CC: and one through CSGnet. Perhaps the CC: list could be culled to include only those not subscribed to CSGnet? Alternatively, just send those who expressed an interest and not CSGnet as a whole.

Bruce

From: Warren Mansell [mailto:wmansell@gmail.com]
Sent: Friday, November 24, 2017 5:30 AM
To: Rupert Young rupert@perceptualrobots.com
Cc: fred@nickols.us; Richard Marken rsmarken@gmail.com; Martin Taylor mmt-csg@mmtaylor.net; joh.orengo@protonmail.com; Sean Mulligan lack.of.inspiration@gmail.com; eetu.pikkarainen@oulu.fi; jlws.wright@optusnet.com.au; johnkirkland@gmail.com; richardpfau4153@aol.com; Bruce Abbott bbabbott@frontier.com; frank.lenk@gmail.com; D Goldstein davidmg@verizon.net; Huddy, Vyv v.huddy@ucl.ac.uk; csgnet@lists.illinois.edu
Subject: Re: LWG: DeepLoco

WM: Seen this folks?

https://www.theguardian.com/science/2017/oct/18/its-able-to-create-knowledge-itself-google-unveils-ai-learns-all-on-its-own

On Wed, Nov 22, 2017 at 11:04 AM, Rupert Young rupert@perceptualrobots.com wrote:

[From Rupert Young (2017.11.22 11.00)]

This is what we have to deal with, counter and show that PCT can do something similar, in a better way,

http://www.cs.ubc.ca/~van/papers/2017-TOG-deepLoco/

It is hierarchical and handles disturbances (watch “Main video”).

I think this would certainly be a possibility of something to aim at for our learning project.

Regards,
Rupert

Dr Warren Mansell
Reader in Clinical Psychology

School of Health Sciences
2nd Floor Zochonis Building
University of Manchester
Oxford Road
Manchester M13 9PL
Email: warren.mansell@manchester.ac.uk

Tel: +44 (0) 161 275 8589

Website: http://www.psych-sci.manchester.ac.uk/staff/131406

Advanced notice of a new transdiagnostic therapy manual, authored by Carey, Mansell & Tai - Principles-Based Counselling and Psychotherapy: A Method of Levels Approach

Available Now

Check www.pctweb.org for further information on Perceptual Control Theory